Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    game developers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Revis
    0.41
     jj
    0.40
     revise
    0.39
    ayang
    0.39
     naughty
    0.39
    تبه
    0.39
     mocha
    0.38
    xie
    0.37
    জেল
    0.37
    깡
    0.37
    POSITIVE LOGITS
    Steve
    0.41
     Steve
    0.40
     steve
    0.39
     Mature
    0.38
     CARR
    0.38
    %{
    0.38
     mature
    0.38
     STE
    0.38
    勝
    0.37
     downloadable
    0.36
    Act Density 0.002%

    No Known Activations